Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2872 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6911. Min Act: -0.0000

Data Index: 511245 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.7273. Min Act: -0.0000

Data Index: 889598 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1414573 (The Pile)

Max Activating Token Index: 997

Text #3

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6481. Min Act: -0.0000

Data Index: 480711 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6239. Min Act: -0.0000

Data Index: 18401 (The Pile)

Max Activating Token Index: 121

Text #5

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6908. Min Act: -0.0000

Data Index: 235618 (The Pile)

Max Activating Token Index: 610

Text #6

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.7273. Min Act: -0.0000

Data Index: 984330 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1370016 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1506818 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6064. Min Act: -0.0000

Data Index: 518524 (The Pile)

Max Activating Token Index: 653

Text #10

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1486188 (The Pile)

Max Activating Token Index: 696

Text #11

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1863883 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6352. Min Act: -0.0000

Data Index: 909127 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1547540 (The Pile)

Max Activating Token Index: 687

Text #14

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1591668 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1229854 (The Pile)

Max Activating Token Index: 662

Text #16

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6672. Min Act: -0.0000

Data Index: 207794 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6207. Min Act: -0.0000

Data Index: 307744 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1162546 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5850. Min Act: -0.0000

Data Index: 540489 (The Pile)

Max Activating Token Index: 849